aliran tensor:: operasi:: ResourceApplyProximalAdagrad

#include <training_ops.h>

Perbarui '*var' dan '*accum' menurut FOBOS dengan kecepatan pembelajaran Adagrad.

Ringkasan

accum += grad * grad prox_v = var - lr * grad * (1 / sqrt(accum)) var = tanda(prox_v)/(1+lr*l2) * max{|prox_v|-lr*l1,0}

Argumen:

  • ruang lingkup: Objek Lingkup
  • var: Harus dari Variabel().
  • accum: Harus dari Variabel().
  • lr: Faktor penskalaan. Pasti skalar.
  • l1: Regularisasi L1. Pasti skalar.
  • l2: Regularisasi L2. Pasti skalar.
  • lulusan: Gradien.

Atribut opsional (lihat Attrs ):

  • use_locking: Jika Benar, pembaruan tensor var dan accum akan dilindungi oleh kunci; jika tidak, perilaku tersebut tidak terdefinisikan, namun mungkin menunjukkan lebih sedikit pertentangan.

Pengembalian:

Konstruktor dan Destruktor

ResourceApplyProximalAdagrad (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input accum, :: tensorflow::Input lr, :: tensorflow::Input l1, :: tensorflow::Input l2, :: tensorflow::Input grad)
ResourceApplyProximalAdagrad (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input accum, :: tensorflow::Input lr, :: tensorflow::Input l1, :: tensorflow::Input l2, :: tensorflow::Input grad, const ResourceApplyProximalAdagrad::Attrs & attrs)

Atribut publik

operation

Fungsi publik

operator::tensorflow::Operation () const

Fungsi statis publik

UseLocking (bool x)

Struktur

tensorflow:: ops:: ResourceApplyProximalAdagrad:: Attrs

Penyetel atribut opsional untuk ResourceApplyProximalAdagrad .

Atribut publik

operasi

Operation operation

Fungsi publik

ResourceApplyProximalAdagrad

 ResourceApplyProximalAdagrad(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input var,
  ::tensorflow::Input accum,
  ::tensorflow::Input lr,
  ::tensorflow::Input l1,
  ::tensorflow::Input l2,
  ::tensorflow::Input grad
)

ResourceApplyProximalAdagrad

 ResourceApplyProximalAdagrad(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input var,
  ::tensorflow::Input accum,
  ::tensorflow::Input lr,
  ::tensorflow::Input l1,
  ::tensorflow::Input l2,
  ::tensorflow::Input grad,
  const ResourceApplyProximalAdagrad::Attrs & attrs
)

operator::tensorflow::Operasi

 operator::tensorflow::Operation() const 

Fungsi statis publik

Gunakan Penguncian

Attrs UseLocking(
  bool x
)